Budget
US$0.27
DeepSeek Coder V3
DeepSeek
Mistral · Budget · US$0.30 input/1M · US$0.90 output/1M · 256K context
Typical monthly cost
US$7.39
≈ per day
US$0.34
Blended cost/1M
US$0.39
Context window
256K
Codestral 25.01 from Mistral is a budget model priced at US$0.30 per 1M input tokens and US$0.90 per 1M output tokens. For a typical solo-developer workload (8 hours/day, 22 days/month — 1 medium feature, 5 small bug fixes, 4 PR reviews, 2 stack-trace debugs, ~1500 lines of TypeScript, 1 large-doc read, with prompt caching at the default mix) Codestral 25.01 costs about US$7/month. The 256K-token context window covers most monorepo scans without truncation.
Move the slider or switch task mix — values update live.
Monthly budget
US$100 / month
≈ $23/wk · ≈ $4.55/day
on Codestral 25.01
Input tokens
283.3M
Output tokens
16.7M
Total tokens
300.0M
Per month this budget delivers
At the default coding-agent mix.
The 22-day month is based on the median working-day count across DE/US.
| Activity | Count | Per task | Daily | Monthly |
|---|---|---|---|---|
| Medium feature (10–15 files) | 1 | US$0.11 | US$0.11 | US$2.38 |
| Small bug fix | 5 | US$0.01 | US$0.05 | US$1.11 |
| PR review | 4 | US$0.01 | US$0.04 | US$0.95 |
| Debug from stack trace | 2 | US$0.02 | US$0.04 | US$0.94 |
| Read a large doc | 1 | US$0.02 | US$0.02 | US$0.36 |
| Micro-interaction (explain / lint fix) | 30 | US$0.00 | US$0.01 | US$0.32 |
| Lines of TypeScript | 1,500 | US$0.00 | US$0.06 | US$1.35 |
| Total | US$0.34 | US$7.39 | ||
The 1500-lines-of-TS row models ~1000 lines read (cache-hit) + ~500 lines written. Headline figures are precise to ~5% — see the FAQ.
What each monthly budget buys on this model (typical solo-developer day, 22 working days).
| Monthly budget | Medium features | PR reviews | Debug sessions | Lines of TS |
|---|---|---|---|---|
| Typical (≈ $7) | 68 | 684 | 347 | 181,208 |
| $50/month | 462 | 4,629 | 2,352 | 1,225,490 |
| $200/month | 1,851 | 18,518 | 9,409 | 4,901,960 |
| $500/month | 4,629 | 46,296 | 23,523 | 12,254,901 |
| $2000/month | 18,518 | 185,185 | 94,095 | 49,019,607 |
Typical mix: coding-agent (85% input, 50% cache hits). Values show the maximum count of each task type at that budget.
Coding
Trained or post-trained for code generation tasks.
Reasoning
Not supported
Multimodal
Not supported
Prompt cache
Not supported
Batch API
50% off when you accept up to 24-hour turnaround.
Tool use
Native function-calling / tool-use API support.
Long context
≥ 200K-token context window.
Extended thinking
Not supported
Total models
2
Median input/1M
US$1.15
Median output/1M
US$3.45
Input range
US$0.30–US$2.00
Verified: 2026-05-07
Running the realistic solo-developer day (1 medium feature + 5 small bug fixes + 4 PR reviews + 2 debug sessions + ~1500 lines of TypeScript + 1 large-doc read, 22 working days) on Codestral 25.01 costs about US$7/month. Heavier workloads scale proportionally; lighter workloads cost less.
256K tokens total, with up to 8K of output. That fits whole repository snapshots, tests included in a single call.
Providers charge US$0.90 per 1M output tokens against US$0.30 per 1M input — output requires real compute, input comes mostly from cache. Coding agents read many files (input-heavy) and emit compact diffs (low output), so total spend is usually input-driven.
No. Every input token is billed at the full US$0.30/1M rate. If your workload reuses the same system prompt frequently, compare against a caching-capable model (Claude Sonnet 4.6, GPT-5) where the effective input rate falls sharply.
Yes, if you can tolerate up to 24-hour turnaround: batch input/output are 50% cheaper than real-time rates. Perfect for nightly code reviews, bulk refactors or pre-merge analysis — wrong for inner-loop editing where you need an answer in seconds.
Open the full calculator with your own budget, task mix and region (US or DE with 19% VAT).
Open calculator